Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5685 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.8153. Min Act: -0.1700
Data Index: 7259263 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.8465. Min Act: -0.1700
Data Index: 1939134 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.6903. Min Act: -0.1700
Data Index: 7255899 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.5965. Min Act: -0.1700
Data Index: 7174926 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.5653. Min Act: -0.1700
Data Index: 3352473 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.5340. Min Act: -0.1700
Data Index: 7255885 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.5340. Min Act: -0.1700
Data Index: 608910 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.5028. Min Act: -0.1700
Data Index: 7255880 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.5028. Min Act: -0.1700
Data Index: 7091895 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.4715. Min Act: -0.1700
Data Index: 557651 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.4715. Min Act: -0.1700
Data Index: 3352474 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.4715. Min Act: -0.1700
Data Index: 7171790 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.4403. Min Act: -0.1700
Data Index: 1769602 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.4090. Min Act: -0.1700
Data Index: 7375442 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.4090. Min Act: -0.1700
Data Index: 7255884 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.4090. Min Act: -0.1700
Data Index: 7255882 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.4090. Min Act: -0.1700
Data Index: 7282916 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.4090. Min Act: -0.1700
Data Index: 7375451 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.3778. Min Act: -0.1700
Data Index: 7255897 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8465. Min Range: -5.8465
Max Act: 5.3465. Min Act: -0.1700
Data Index: 7255898 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19